帮助 关于我们

返回检索结果

基于卷积神经网络与光谱特征的夏威夷果品质鉴定研究
Study on Quality Identification of Macadamia nut Based on Convolutional Neural Networks and Spectral Features

查看参考文献11篇

杜剑 1,2   胡炳樑 1 *   刘永征 1   卫翠玉 1   张耿 1   唐兴佳 1  
文摘 夏威夷果含油量高,在开缝之后容易发生变质,现有关于夏威夷果品质鉴定的方法多为传统的破坏性检验,很难满足无损检测的需求。卷积神经网络(CNN)作为应用最广泛的深度学习网络模型之一,具有比浅层学习方法更强的特征提取与模型表达能力,在光谱数据方面的应用拥有很大潜力。基于夏威夷果在可见-近红外的光谱特征分析,研究用于提取夏威夷果光谱特征的卷积神经网络模型,并提出一种高效无损鉴定夏威夷果品质的方法。首先以三种不同品质的夏威夷果(好籽、哈籽及霉籽)为研究对象,分析样本在500~2 100nm的光谱信息;在光谱数据预处理中引入白化处理方法,用以增强数据的相关性差异;然后在模型训练过程中,将样本随机分为训练集和预测集,探讨不同CNN结构、卷积层数、卷积核大小及个数、池化层类型、全连接层神经元个数以及激活函数对分类结果的影响,并采用激活函数ReLU和Dropout方法,预防样本数据过少引起的过拟合现象;最后通过分析模型分类准确率和计算效率,确定了一个6层结构的CNN模型:输入层—卷积层—池化层—全连接层(200神经元)—全连接层(100神经元)—输出层。实验结果表明:上述网络模型对校正集和预测集的分类准确率均达到100%。因此,改进后的卷积神经网络模型可充分学习夏威夷果的光谱特征并有效分类,将深度学习理论与光谱分析相结合的方法能够实现对夏威夷果品质的准确鉴定,同时为夏威夷果等坚果类食品的高效、无损、实时在线检测提供了新思路。
其他语种文摘 Macadamia nut is easy to spoil after being stripped off because of the high level of oil in it.Most of the existing traditional methods are destructive which are difficult to satisfy the demand of non-destructive detection.As one of the widely used deep learning models,convolutional neural network(CNN)has stronger capabilities of feature extraction and model formulation than shallow learning methods and great potential for the application of spectral data.We studied suitable CNN architecture to extract spectral features of Macadamia based on Vis-NIRS analysis,and proposed an efficient non-destructive method to identify the quality of Macadamia.At first,we took three kinds of macadamia nut with different qualities(including better nut,worse nut and moldy nut)as the research object and analyzed the spectral information in the wavelength range of 500~2 100nm.We introduced the concept of whitening in data preprocessing to strengthen the correlation difference.In the process of model training, we divided the sample into training set and prediction set randomly and then discussed the effects of different structure parameters, such as the number of convolution layer,size of convolution kernel,pooling type,number of neuron in full connection layer and activation function.We applied ReLU and Dropout to prevent over-fitting caused by lack of data.At last,through the analysis of the classification accuracy and computational efficiency,a CNN model of 6-layer structure was established:input layer- convolution layer-pooling layer-full connection layer(including 200neurons)- full connection layer(including 100neurons)- output layer.The results show that the final classification accuracy of the calibration set and prediction set reached 100%.This improved CNN model can fully learn the spectral features of macadamia and classify effectively.The combination of the deep learning theory and the spectral analysis method can identify the quality of macadamia accurately,and provide a new idea for the efficient, non-destructive,real-time,online detection of macadamia and other nuts.
来源 光谱学与光谱分析 ,2018,38(5):1514-1519 【核心库】
DOI 10.3964/j.issn.1000-0593(2018)05-1514-06
关键词 可见-近红外光谱 ; 夏威夷果 ; 深度学习 ; 卷积神经网络 ; 品质鉴定
地址

1. 中国科学院西安光学精密机械研究所, 中国科学院光谱成像技术重点实验室, 陕西, 西安, 710119  

2. 中国科学院大学, 北京, 100039

语种 中文
文献类型 研究性论文
ISSN 1000-0593
学科 化学
基金 国家自然科学基金项目
文献收藏号 CSCD:6243807

参考文献 共 11 共1页

1.  刘建福. 中国食物与营养,2005,2:25 被引 1    
2.  Schmutzler M. Vibrational Spectroscopy,2014,72:97 被引 5    
3.  Ferreira D S. Food Control,2015,48:91 被引 6    
4.  Miphokasap P. Remote Sensing,2012,4(6):1651 被引 7    
5.  Jakobek L. Journal of Food Composition and Analysis,2016,45:9 被引 2    
6.  Vanoli M. Postharvest Biology and Technology,2014,91:112 被引 11    
7.  Hinton G E. Science,2006,313(5786):504 被引 1661    
8.  Lecun Y. Proceedings of the IEEE,1998,86(11):2278 被引 1979    
9.  Chen Y. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(6):2094 被引 44    
10.  Sainath T N. Proceedings of the 38th IEEE International Conference on Acoustics(ICASSP'13),2013:8614 被引 1    
11.  Abdel-Hamid O. Proceedings of the IEEE International Conference on Acoustics(ICASSP'12),2012:4277 被引 1    
引证文献 6

1 李琳娜 基于GRNN的水下爆炸容器动态响应预测 爆破,2018,35(4):141-146
被引 0 次

2 路皓翔 基于压缩自编码融合极限学习机的柑橘黄龙病鉴别方法 分析化学,2019,47(5):652-660
被引 2

显示所有6篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号